AI 中文总结
针对持续AI生成图像检测中的双重退化问题，提出解耦式框架DECODE，结合SDR与CDA技术，在19个领域上实现高准确率且遗忘率极低，还能泛化至未见过的生成器。
AI 中文摘要
随着生成模型不断发展，AI生成图像检测器必须逐步适配新兴的生成领域，同时保留从先前领域获取的知识。这种持续学习场景极具挑战性，因为取证痕迹通常细微且与生成器相关，导致检测器极易遭受灾难性遗忘。现有方法主要通过稳定特征表征来解决该问题，隐含地将遗忘视为表征层面的问题。本文表明，这一视角并不完整。我们证实，即便特征表征仍具判别性，决策边界也会因分类头在新领域持续优化而逐渐偏移。这两种效应共同引发了一种复合失效模式，称为双重退化。为应对这一挑战，我们提出DECODE，一种解耦式持续检测框架，可同时缓解表征层面与决策层面的遗忘。具体而言，我们引入子空间多样性正则化（Subspace Diversity Regularization，SDR）以保留多样的取证表征，并采用闭式决策对齐（Closed-Form Decision Alignment，CDA）在每次适配器合并后重新校准共享分类头，无需手动调整超参数。在19个生成领域上开展的大量实验表明，DECODE的平均准确率达99.36%，仅存在0.39%的遗忘，同时对11个未见过的生成器的泛化准确率达95.36%。
英文摘要
As generative models continue to evolve, AI-generated image detectors must incrementally adapt to emerging generative domains while preserving knowledge acquired from previous ones. This continual learning setting is particularly challenging because forensic traces are often subtle and generator-specific, making detectors highly vulnerable to catastrophic forgetting. Existing methods primarily address this problem by stabilizing feature representations, implicitly treating forgetting as a representation-level issue. In this paper, we show that this perspective is incomplete. We demonstrate that even when feature representations remain discriminative, the decision boundary can progressively drift as the classification head is continually optimized on new domains. These two effects jointly give rise to a compound failure mode, termed Dual Degradation. To overcome this challenge, we propose DECODE, a decoupled continual detection framework that jointly mitigates representation- and decision-level forgetting. Specifically, we introduce Subspace Diversity Regularization (SDR) to preserve diverse forensic representations and Closed-Form Decision Alignment (CDA) to recalibrate the shared classification head after each adapter merge without manual hyperparameter tuning. Extensive experiments on 19 generative domains show that DECODE achieves an average accuracy of 99.36% with only 0.39% forgetting, while further generalizing to 11 unseen generators with 95.36% accuracy.
